EMoDi: Entity-Enhanced Momentum-Difference Contrastive Learning for Semantic-Aware Verification of Scientific Information

被引：0

作者：

Yang, Ze ^{[1
]}

Sun, Yimeng ^{[1
]}

Nakaguchi, Takao ^{[1
]}

Imai, Masaharu ^{[1
]}

机构：

[1] Kyoto Coll Grad Studies Informat, Sch Appl Informat Technol, Kyoto, Japan

来源：

2023 IEEE INTERNATIONAL CONFERENCE ON KNOWLEDGE GRAPH, ICKG | 2023年

关键词：

scientific information verification; entity-enhancement; noise-ignoration; two-step prediction; contrastive learning;

D O I：

10.1109/ICKG59574.2023.00023

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper proposes the EMoDi system to improve the performance of the entire scientific information verification pipeline. First, the Momentum-Difference contrastive learning framework is introduced to capture more semantics information. In abstract retrieval, entity-enhancement and noise-ignoration are introduced to improve the ability to retrieve relevant abstracts more accurately. In addition, a two-step verification method is used in label prediction to improve the label prediction ability and reduce the false positive rate of the " NOT ENOUGH INFO" label. The proposed pipeline outperforms the baseline VERISCI and QMUL-SDS. The code of this system is available on GitHub.

引用

页码：142 / 151

页数：10